Overview

Position Title: Senior AI Engineer, AI Labs

Responsibilities

• Location: Noida, India. Hybrid, with regular overlap with US hours.
• Reports to: Head of Procurement Partners AI Labs
• Procurement Partners is the procure-to-pay platform for healthcare. Thousands of post-acute and non-acute care organizations use our software to automate purchasing, inventory, invoicing, and payments — skilled nursing, senior living, behavioral health, home care, physician practices, and surgery centers, plus the group purchasing organizations serving them. Every hour our customers stop spending on procurement goes back into patient care.
• If you have a passion for technology, enjoy providing value to customers, and are looking for a company that will help you develop your career, we want to talk to you!
• AI Labs is a small applied group inside an established engineering organization that takes emerging technology from idea to production and hands it to the teams who own it. Today that technology is AI; in two years it may be something else, so we hire for people who have gone deep on an emerging technology and shipped with it. Current depth matters; the ability to do it again matters more.
• The near-term agenda: AI over our data, semantic search across our products, and an agentic platform where agents learn from feedback and take on autonomous work. A Senior Data Scientist owns the predictive and decision models, and many become tools your agents call.
• This is a research engineering role. You will find opportunities, prove or kill them quickly, and productize the ones that survive.
• Diagnose before building: map how the work is done today, find the constraint, and confirm the technology fits.
• Build natural-language querying over our structured and unstructured data, including structure extracted from invoices and contracts.
• Build semantic search spanning our products, delivered as a single entry point.
• Build the agentic platform: orchestration, the tool interface standard and registry, memory, budgets, retries, fallbacks, and human checkpoints.
• Close the loop on agent behavior: capture production feedback and apply the right technique — offline evaluation, preference data, bandits, or reinforcement learning — so agents improve and take on autonomous work.
• Build evaluation infrastructure: task datasets, failure taxonomies, regression suites wired into release, and LLM-as-judge calibrated against human agreement.
• Design guardrails: prompt injection defense, output filtering, access control, and audit trails.
• Own model cost: routing on quality, latency, and price.
• Own initiatives end to end, through production and iteration, including a clean handoff to the owning team.

Qualifications

• Carried ideas from open question to production in a small, autonomous group, often as the first or only person on the problem: framing it, building it, measuring honestly, and knowing when to stop.
• 8+ years of professional software engineering, including at least two years building AI systems that reached production and stayed there.
• At least one AI feature shipped to real users, instrumented, and measurably improved from production feedback after launch.
• Distributed systems and event-driven architecture: asynchronous messaging, streams, idempotency, and eventual consistency. Our target state is event-driven.
• Retrieval: chunking, hybrid and semantic search, reranking, and measuring retrieval quality separately from answer quality.
• Prompt and context engineering, agentic patterns (tool use, planning and critic loops, orchestration), and model-choice judgment not tied to one provider's abstractions.
• Evaluating generative systems: eval sets, regression suites, and how you decided one model or prompt version was better — sample size, variance, and what the eval did not cover.
• Guardrail design: prompt injection defense, output filtering, access control, and audit trails.
• Python and SQL, and production engineering habits: tests, containers, CI, maintainable code.
• Deploying and running systems in the cloud. We are an AWS shop; equivalent depth on any cloud transfers.
• Presenting what was built, what it does not do, and what you recommend next to an executive audience.
• Bachelor's degree in a quantitative or technical field.
• Reinforcement learning, including RLHF, RLAIF, or reward modeling for agent behavior.
• Document AI: extracting structure from scans, handwriting, and tables at production accuracy.
• B2B procurement or healthcare procurement domain experience.
• Text-to-SQL or semantic-layer work over a production schema.
• Fine-tuning and post-training, or self-hosted inference.
• Master's and/or PhD in a quantitative or technical field.
• Published research, granted or filed patents, or significant open-source work.
• Operating what you ship — monitoring, tracing, latency, cost. Platform support is provided.
• Professional certification in AI, machine learning, cloud, or software engineering.