About client:
A global IT and consulting company based in Bangalore, India, providing IT services to clients worldwide across multiple industries.
About the Role
We are seeking a highly technical, hands-on Senior Individual Contributor (IC) to architect, build, and productionize our next-generation, enterprise-grade multi-agent AI systems at scale.
In this role, you will operate across the entire agentic stack—from orchestration and model management to advanced RAG, enterprise observability, and rigorous evaluation. You will play a pivotal role in shifting our AI capabilities from experimental prototypes to resilient, secure, and production-hardened enterprise systems.
Key Responsibilities
* Agent Orchestration & Architecture: Design and deploy production-grade multi-agent workflows using advanced frameworks (e.g., LangGraph, CrewAI, AutoGen). Implement complex orchestration patterns including intent detection, dynamic routing, state management, and hierarchical topologies.
* Tool & Protocol Integration: Build and govern Model Context Protocol (MCP) servers to expose enterprise tools, internal systems, APIs, and data sources as structured, auditable agent tool surfaces. (Knowledge of A2A is highly advantageous).
* AI Gateways & Governance: Configure and scale AI Gateway platforms (LiteLLM, AWS Bedrock, Azure API Management, or Apigee AI Extensions) for multi-model routing, cost optimization, quota enforcement, and automated model fallback.
* Responsible AI & Security: Integrate robust guardrails—including PII masking, content moderation, toxicity filtering, and strict policy enforcement—directly into the model invocation layer. Implement security-first engineering aligned with the Agent Development Lifecycle (ADLC).
* RAG Optimization: Own the design and end-to-end optimization of our RAG pipelines, managing chunking strategies, embedding model selection, hybrid retrieval, reranking, and active hallucination mitigation.
* Evaluation & Observability: Establish production LLM evaluation frameworks (golden test sets, regression suites, LLM-as-a-judge, online A/B testing) and implement red-teaming for prompt injection and adversarial inputs. Track and optimize system performance via enterprise observability platforms (e.g., Langfuse).
* CI/CD & DevOps: Support and contribute to modern CI/CD pipelines tailored for agentic systems, utilizing containerized deployments, automated behavioral testing, feature flags, and progressive rollout strategies.
What We Are Looking For
* Core Engineering Foundation: 6+ years of experience in enterprise backend engineering, microservices architecture, and cloud infrastructure (Docker, Kubernetes, CI/CD pipelines).
* Agentic AI Expertise: 2+ years of hands-on experience building and deploying production-level LLM applications, with a strong focus on state machines, multi-agent frameworks, and advanced RAG.
* Security & Governance Mindset: A strong understanding of least-privilege tool access, sandboxed execution, and full audit traceability within data-sensitive environments.
* Tooling Proficiency: Deep familiarity with Python or TypeScript, modern API Gateways, and AI observability tools.
Experience: 6 + Years
Rate: 500 GBP / day
Location: London
Sector: Banking
Work style: Hybrid ( 2- 3 days in office per week)
Urgent Hiring
About HR Ways:
HR Ways is an Award winning Technical Recruitment Firm helping software houses and IT Product companies internationally and locally to find IT Talent. HR Ways is engaged by 300+ Employers worldwide ranging from worlds biggest SaaS Companies to most competitive Startups. We have entities in Dubai, Canada, US, UK, Pakistan, India, Saudi Arabia, Portugal, Brazil and other parts of the world.