The Role: We are hiring a hands-on Tech Lead to own a pod of 4-6 engineers within our Knowledge Management / NLP org, or across adjacent agentic AI platform pods depending on fit. You will design and ship production systems that power enterprise knowledge retrieval, grounding, and agentic reasoning across the Leena.ai platform, the engine behind every customer-facing agent. This is an IC-heavy leadership role. Expect to spend roughly 60-70% of your time in code, architecture, and design reviews, and 30-40% on mentoring, planning, and cross-functional alignment.

What You ll Own

Knowledge agent architecture: Architect and ship production RAG, knowledge ingestion, and agentic reasoning pipelines that operate across enterprise systems of record (Workday, ServiceNow, SAP, Confluence, SharePoint, and many more).
Evaluation quality: Build and maintain custom golden datasets and eval harnesses; distinguish retrieval failures from generation failures; set and enforce production accuracy, latency, and cost SLOs.
Multi-LLM orchestration: Work across Anthropic, OpenAI, and Gemini model families. Own model selection tradeoffs (capability vs. cost vs. latency), prompt iteration, function-calling/tool-use patterns, and fallback strategies.
Technical leadership: Set the engineering bar for the pod design docs, code reviews, on-call discipline, incident response, and production quality gates.
Platform leverage: Partner with Product and Implementation on reference architectures that compress time-to-value for new enterprise deployments.
People growth: Mentor 4-6 engineers; grow at least one to senior-level scope within the year.

Must-Haves

5+ years of software engineering experience with a track record of shipping production software.
Strong production engineering in Python and Node.js. Comfort reading and contributing to a React frontend when the work crosses the boundary.
Hands-on experience building LLM-powered production systems with at least one major provider (Anthropic, OpenAI, or Gemini): RAG pipelines, function-calling / tool-use, prompt and eval iteration loops.
Depth in one or more of: information retrieval, NLP, knowledge graphs, semantic search, vector databases, or chunking / embedding strategies.
Production ownership on AWS observability, cost discipline, and incident response, not just familiarity.
Demonstrated ability to instrument evals that separate retrieval failures from generation failures, and to drive accuracy improvements off that signal.
Track record of shipping customer-facing features in enterprise SaaS environments.

Strong Pluses

Experience with agentic orchestration frameworks (LangGraph, CrewAI, AutoGen) or having built equivalent orchestration in-house.
Hands-on with evaluation tooling: RAGAS, DeepEval, LangSmith, Arize Phoenix; familiarity with benchmarks like CRAG.
Experience working across multiple LLM providers in production (routing, fallback, cost/latency-aware model selection).
Enterprise security and compliance exposure: SOC 2, ISO 27001, GDPR, data residency, PII handling.
Experience with enterprise integrations: ITSM, HRIS, ERP, or collaboration systems (Workday, ServiceNow, SAP SuccessFactors, Oracle, Confluence, SharePoint).
Prior Series B D startup experience and comfort operating with ambiguity.

How You Will Be Measured (First 6 Months)

Pod velocity and quality: on-time delivery of two quarterly roadmap themes with defensible evaluation results.
Production reliability: meeting SLOs for accuracy, latency, availability, and cost per resolved query.
Platform leverage: reusable components, primitives, or patterns your pod contributes that other teams adopt.
Team growth: measurable progression of at least one engineer on your pod; healthy retention and engagement.

Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.

Technical Lead

Job Description

No Referrers Available