Gen AI Lead Developer at HEXAWARE
, , India -
Full Time


Start Date

Immediate

Expiry Date

03 Sep, 26

Salary

0.0

Posted On

05 Jun, 26

Experience

10 year(s) or above

Remote Job

Yes

Telecommute

Yes

Sponsor Visa

No

Skills

LangChain, LlamaIndex, Multi-agent Orchestration, Vector Databases, LLMOps, Kubernetes, Terraform, gRPC, REST, FAISS, Milvus, Pgvector, MLflow, W&B, CI/CD Integration, Software Testing

Industry

IT Services and IT Consulting

Description
• Years of experience: 10+ years total; 5+ in AI/ML systems; 2+ with LLMs/agentic systems. • Summary: Own the end-to-end technical architecture for a testing agentic AI platform: multi-agent orchestration, tool interfaces, safety, observability, and scalable deployment. • Responsibilities: a. Define multi-agent system architecture (planner, executor, memory, tool adapters) and governance. b. Design tool-use layer (APIs, search, code, test frameworks) and secure sandboxing, reflecting that agentic systems act via tools and feedback loops c. Establish evaluation and safety architecture (guardrails, red-teaming, policy engines) for non-deterministic behavior and human-in-the-loop review d. Select model strategy (proprietary vs OSS), vector/store strategy, and retrieval patterns. e. Drive platform non-functionals: reliability, latency, cost, observability, and data privacy. f. Partner with PO/AI Lead on roadmap and technical debt management; collaborate with product to design, test, and deploy AI capabilities • Technical skills: a. LLM/agent frameworks (LangChain/LlamaIndex), multi-agent orchestration, tool-calling, function calling. b. Retrieval + memory: vector DBs (FAISS, Milvus, pgvector), embeddings. c. Evaluation/LLMOps: prompt/versioning, offline/online evals, MLflow/W&B, feature stores. d. Systems: distributed services, eventing, gRPC/REST, Kubernetes, Terraform, observability. e. Security/compliance: data governance, PII handling, secrets, guardrails. • Domain skills: a. Software testing/QA platforms, test orchestration, CI/CD integration. b. Agentic behavior patterns and test generation/coordination at scale
Responsibilities
Own the end-to-end technical architecture for a testing agentic AI platform, focusing on multi-agent orchestration and tool interfaces. Establish evaluation, safety guardrails, and scalable deployment strategies for non-deterministic AI behavior.
Loading...