I lead AI and engineering at Eightfold AI, building agents for Fortune 1000 enterprises. Before that: consumer agents used by millions at a major frontier AI lab, conversational AI at Amazon Alexa, contextual search at Walmart.com, and the world’s first e-commerce machine translation at eBay.
Ask about the agents I have shipped, how I would approach your problem, or how to work together. Answers come from my track record on this site. Type help for commands.
PANKAJ RAJAN
Head of AI & Engineering · agents from pilot to production
Ask a question in plain English, or type help.
AI systems I architected and led to production, each with the number it moved.
Ship consumer agents people trust, for millions of daily users.
Architected the agent platform, with guardrails and a knowledge base, and built several consumer agents on it: shopping, on-demand RAG, and customer service.
Slow build cycles. Engineers buried in support, triage, reporting, and migrations.
Made AI the default way we build: prototype with AI, validate with customers, then ship. Agents now run support, triage, SLA alerts, and exec and MBR reporting, and any team can launch its own from a YAML config. Near-flat headcount; two new initiatives launched.
Every product line needed agents. None could afford its own stack.
Built one shared platform — runtime, memory, tools, guardrails, evals, tenant isolation — and took agentic products from first code to production on it, including a conversational analyst that turns plain-language workforce questions into answers.
Raise open-domain quality without raising serving cost.
Built the evaluation system for conversational agents that gated every model change, an early knowledge service (RAG) that grounded open-domain dialogue, and classifiers for intent detection, anti-hallucination, and safety.
Enterprises had knowledge-work problems and data, but no fast, trustworthy path to a working model.
Built an end-to-end no-code platform: data quality scored against goals, synthetic data enrichment, bias detection, baseline models, and an evaluation harness — blending classical ML, generative AI, and statistics. Delivered as multi-tenant SaaS, certified SOC 2 Type II.
Customers needed AI on sensitive data and real workflows, with ROI they could measure.
Defense: software and a deployment strategy that met FedRAMP requirements, letting teams process sensitive data through no-code workflows in an isolated environment. Publishing: an AI copy-editing workflow that cut cost 80% and raised throughput with the existing workforce. Learning: AI coaches that help students learn in multiple languages. University recruiting: for a large EdTech vendor, data analysis and prediction models that pinpointed the right top-of-funnel population to reach.
Long-tail queries were misunderstood, and proving out a new ranking algorithm took months of costly A/B tests.
Founded the Query Understanding team for contextual search — entity extraction, intent classification, and query rewriting — and built an evaluation harness using Bayesian belief networks and click models to test ranking algorithms before they reached A/B tests.
Cross-border buyers could not read listings in their own language.
As the second engineer on eBay’s machine translation system, worked across the entire pipeline — from conception and model building to evaluation and deployment — opening cross-border marketplaces to buyers in their own language.
Weighing an agent program, an AI hire, or an AI investment? Bring the decision to a 30-minute session.
Book a 30-min sessionI have spent 15+ years building AI that real people use — and the last decade leading the teams and companies that build it.
At Eightfold AI, I lead AI and engineering for the company’s agentic products: the shared platform agents run on, and the agents, assistants, and analytics built on top of it. I have also architected the agent platform, with guardrails and a knowledge base, and built consumer agents on it for a major frontier AI lab with millions of daily active users. Earlier, as co-founder and CPTO of MarkovML, I raised $8M and built a no-code, data-centric ML SaaS platform for enterprise knowledge work, certified to SOC 2 Type II. Before that, I built evaluation, knowledge (RAG), and safety systems for open-domain dialogue at Amazon Alexa, founded the Query Understanding team behind Walmart.com contextual search, and was the second engineer on eBay’s machine translation engine, the world’s first built for e-commerce.
I write about what I have learned building these systems, and I make time each month for a few sessions with founders, leaders, and investors working through the same problems.
Where enterprise AI is heading — digital workers, long-horizon agents, and governed agent platforms — built on the search and machine learning that make them reliable.
Lead AI and engineering across talent management, agentic candidate experiences, career coaching, talent design, and workforce readiness — products used by Fortune 1000 enterprises.
Lead the evolution of the agentic platform, combining reasoning models, retrieval, grounding, tool use, predictive ML, and evaluation, and set technical direction across orchestration, enterprise integrations, security, tenant isolation, data residency, and production reliability.
Built a no-code, end-to-end data-centric ML SaaS platform — data quality against goals, synthetic data enrichment, bias detection, baseline models, and an evaluation harness — combining classical ML, generative AI, and statistics for everyday enterprise knowledge work.
Led a 35-person company across engineering, platform, security, and go-to-market. Raised $8M and sold into defense (FedRAMP-compliant deployment) and EdTech (−80% copy-editing cost for publishers, multilingual AI coaching for students), achieved SOC 2 Type II, and presented strategy and risk to the board. Merged into Zig.ai in 2025.
Built the evaluation system for conversational agents that gated every model change before production, an early knowledge service (RAG) for the open-domain dialogue system, and classifiers for intent detection, anti-hallucination, and safety.
Worked on early large language models for open-domain dialogue, alongside response ranking and knowledge graphs. Doubled the user rating to 3.7/4, cut latency by over 40%, and reduced cost to serve by ~15%.
Raised pre-seed funding and launched a multimodal conversational shopping assistant.
Wound down when COVID closed retail, returning remaining capital to investors.
Founded the Query Understanding team behind Walmart.com contextual search, improving long-tail understanding by 85%.
Built an evaluation harness using Bayesian belief networks and click models that cut the time to launch new ranking algorithms from months to days and caught costly A/B test mistakes before they shipped.
At Ayasdi AI, architected and built the supervised machine learning platform on topological data analysis — unlocking several million dollars in new revenue in its first year across healthcare, finance, and fraud detection.
Before that, the second engineer on eBay’s machine translation engine, the world’s first for e-commerce: worked across the entire pipeline, from conception and model building to evaluation and deployment, adding $1B+ in GMV. Earlier roles at Microsoft and AMD.
Positions earned building these systems, and how I think about every new one.
AI lets one person prototype and reach product-market fit faster than ever. But making it work once is a milestone; making it work the thousandth time, for the millionth user, is engineering. The opportunity for leaders is to turn that speed into operational discipline.
Read the essayAI made output cheap and understanding expensive. When AI writes and AI reviews, understanding fades — until a system misbehaves at midnight. The engineers who understand the system, make the tradeoffs, and own the outcome are where the value is.
Read the essayMost agent programs stall because nobody can say whether this week’s version is better than last week’s. Teams that gate every release on task-level evals ship faster and break less.
An agent is only as good as what it can find. Query understanding, retrieval, and ranking — disciplines refined over two decades of e-commerce search — decide whether an agent answers or guesses.
What I look for in an AI company. I have raised capital, built the platforms, and hired the teams; I have run technical diligence within the Superset Ventures portfolio, and I angel invest on my own.
What remains valuable when frontier models improve next quarter: proprietary data, workflow depth, distribution.
Whether the system can scale in users, tenants, and use cases without a rewrite — and where the debt sits.
How quality is measured and gated before release. Teams without evals are shipping demos.
Inference, retrieval, and human-review cost per outcome, and how it trends as usage grows.
Security, tenant isolation, compliance, and private deployment — what large customers will demand in procurement.
Whether the technical leadership can hire, ship, and make sound build-versus-buy decisions at the next stage.
A few hours each month I hold free 30-minute 1:1 sessions with founders, executives, and investors. Bring one decision you are weighing — where agents will actually pay off in your business, how to take an agent pilot to production, how to lead an engineering team through AI transformation, or how to judge an AI company’s defensibility — and leave with a clear point of view and next steps.
or email pankaj@pankajrajan.comWhether you are building with AI, leading a team through it, or backing a company that depends on it, I am glad to compare notes. I respond within two business days.