Job Description
Mandatory Skills
Core: AutoGen, Pydantic AI, Python, Langfuse, Mem0 + Redis, RAG pipeline (vector search + retrieval), Embedding models
Preferred Skills : Pipecat, LangChain, ChromaDB
Job Description / Roles & Responsibilities (in Detail) Stack:
Core: AutoGen, Pydantic AI, Python, Langfuse, Mem0 + Redis, RAG pipeline (vector search + retrieval), Embedding models
Optional: Pipecat, LangChain, ChromaDB
Scope:
Design and orchestrate multi-agent systems using AutoGen & Pydantic AI
Implement RAG pipelines, memory management, and observability with Langfuse
Integrate security, performance, and quality gates into production systems
Prompt & Context engineering incl. memory management.
Guardrails:
Implement policy enforcement for prompt injection prevention
Add role-based access control (RBAC) for agent actions
Validate tool invocation safety and restrict sensitive operations
Apply content filtering for PII and compliance-sensitive data
Security & Compliance: OAuth2/OIDC, JWT, secrets management (Azure Key Vault/HashiCorp Vault), PII redaction
Quality/Evals: Writing & monitoring Eval scores, A/B experiments; Langfuse metrics as quality gates
Performance: Async workers (Celery/RQ), batching, Redis caching strategies
Observability: OpenTelemetry integration; dashboards for latency, throughput, error rates, token/cost
Experience: 5–8 years in software engineering, with recent hands-on experience in AI/LLM systems (1–2 years), strong OOP and dynamic programming skills
͏
͏
͏
Mandatory Skills
Core: AutoGen, Pydantic AI, Python, Langfuse, Mem0 + Redis, RAG pipeline (vector search + retrieval), Embedding models
Preferred Skills : Pipecat, LangChain, ChromaDB
Job Description / Roles & Responsibilities (in Detail) Stack:
Core: AutoGen, Pydantic AI, Python, Langfuse, Mem0 + Redis, RAG pipeline (vector search + retrieval), Embedding models
Optional: Pipecat, LangChain, ChromaDB
Scope:
Design and orchestrate multi-agent systems using AutoGen & Pydantic AI
Implement RAG pipelines, memory management, and observability with Langfuse
Integrate security, performance, and quality gates into production systems
Prompt & Context engineering incl. memory management.
Guardrails:
Implement policy enforcement for prompt injection prevention
Add role-based access control (RBAC) for agent actions
Validate tool invocation safety and restrict sensitive operations
Apply content filtering for PII and compliance-sensitive data
Security & Compliance: OAuth2/OIDC, JWT, secrets management (Azure Key Vault/HashiCorp Vault), PII redaction
Quality/Evals: Writing & monitoring Eval scores, A/B experiments; Langfuse metrics as quality gates
Performance: Async workers (Celery/RQ), batching, Redis caching strategies
Observability: OpenTelemetry integration; dashboards for latency, throughput, error rates, token/cost
Experience: 5–8 years in software engineering, with recent hands-on experience in AI/LLM systems (1–2 years), strong OOP and dynamic programming skills
͏
Experience: 8-10 Years .
Reinvent your world. We are building a modern Wipro. We are an end-to-end digital transformation partner with the boldest ambitions. To realize them, we need people inspired by reinvention. Of yourself, your career, and your skills. We want to see the constant evolution of our business and our industry. It has always been in our DNA - as the world around us changes, so do we. Join a business powered by purpose and a place that empowers you to design your own reinvention.