Agentic Forward Deployed Engineer

HCLTech; Greater London; On-site; GBP 30,000 - 50,000; Full time

Job summary

HCLTech is seeking a hands-on Agentic Forward Deployed Engineer to embed with clients and build business transformation agents using Python and leading ADKs.

You will design single-agent and multi-agent systems, drive rapid prototypes, and deliver production-grade solutions with secure, auditable DevSecOps practices. The role emphasizes mentoring a lean team and delivering measurable ROI across enterprise workloads.

Qualifications

• Strong Python engineering with typed, tested and packaged code.
• Hands-on agent building with at least one ADK.
• Solid command of agent engineering including tool/call and MCP integration.
• Experience with eval-driven development and enterprise software practices.

Responsibilities

• Embed with stakeholders and frame business processes as agentic solutions.
• Stand up working agent prototypes quickly.
• Design and ship single-agent and multi-agent systems in Python using ADKs.
• Drive delivery and operational efficiency with measurable ROI.
• Apply prompt engineering, context engineering, and RAG retrieval.
• Connect agents into client ecosystems via secure APIs and authentication.
• Build reusable agent components, tool libraries and templates with guardrails.
• Prototype quickly and harden solutions into production-grade Python.
• Build evaluation harnesses and test suites for safety and correctness.
• Own AgentOps/DevSecOps including CI/CD, telemetry and governance.
• Feed production telemetry and client feedback back into prompts and design.
• Adopt evolving agent frameworks and share field learnings.
• Lead and mentor a lean team of 3 agent engineers.

Skills

Python engineering

Agent development

Prompt engineering

RAG / context engineering

Multi-agent orchestration

DevSecOps

Leadership

Tools

Google ADK

LangGraph

CrewAI

OpenAI Agents SDK

AWS Bedrock AgentCore

Microsoft Agent Framework / Semantic Kernel

Job description

Salary: £30,000 - 50,000 per year

Requirements

• Strong Python engineering with idiomatic, typed, tested and packaged code, grounded in solid software engineering principles such as design, version control and architecture.
• Hands-on agent building experience with at least one agent development kit such as Google ADK, LangGraph, CrewAI, OpenAI Agents SDK, AWS Bedrock AgentCore or Microsoft Agent Framework / Semantic Kernel.
• Solid command of agent engineering, including prompt engineering, context engineering, prompt caching, RAG / context graphs, tool / function calling, MCP and multi-agent orchestration.
• Experience with eval-driven development, including designing evaluation harnesses and measuring agent quality, safety and reliability.
• Experience with standards-based integration and DevSecOps, including APIs, secure auth, CI/CD, observability and AgentOps.
• Ability to conceptualize business problems as agents quickly and operate effectively in ambiguous, customer-embedded settings.
• Client-facing maturity with the ability to translate between technical and non-technical stakeholders and own outcomes.
• Experience mentoring or leading small engineering teams.
• Strongly preferred: fluency across multiple ADKs and the judgment to select the right one per engagement.
• Strongly preferred: experience deploying agents to managed runtimes at enterprise scale with governance and cost control.
• Strongly preferred: domain depth in finance operations, supply chain, HR, claims or compliance.
• Strongly preferred: experience with an enterprise agent platform, including Responsible AI and governance at scale.
• Strongly preferred: track record of turning agents into reusable accelerators or IP adopted beyond a single engagement.

Responsibilities

• Embed with stakeholders and frame business processes as agentic solutions.
• Stand up working agent prototypes in days, not weeks.
• Design and ship single-agent and multi-agent systems in Python using ADKs that automate and transform real client workflows with measurable ROI.
• Drive delivery efficiency and operational efficiency, including shorter cycle times, less manual effort, higher accuracy and lower cost-to-serve.
• Apply prompt engineering, context engineering, prompt caching, RAG / context-graph retrieval, memory, tool / function calling, MCP integration and multi-agent orchestration.
• Connect agents into client ecosystems through proven integration patterns, standards-based APIs and secure authentication.
• Build reusable agent components, skills, tool libraries and templates, and add guardrails for predictable, safe and repeatable behaviour.
• Prototype quickly using the kits scaffolding, then harden solutions into production-grade, well-tested Python.
• Build evaluation harnesses and test suites to measure agent correctness, safety and regression before release.
• Own AgentOps / DevSecOps, including CI/CD for agents, versioning, observability, telemetry, shift-left security and Responsible AI governance.
• Feed production telemetry, evals and client feedback back into prompts, context and agent design.
• Adopt evolving agent frameworks and patterns quickly and bring field learnings back to the practice.
• Lead and mentor a lean team of 3 agent engineers, set technical direction and raise the engineering bar.

Technologies

• Agentic AI
• AI
• AWS
• CI/CD
• Cloud
• DevSecOps
• Embedded
• LESS
• MCP
• Python
• RAG
• Security
• Azure
• LLM

More

We are HCLTech, a global technology company with more than 220,000 people across 60 countries, delivering capabilities across digital, engineering, cloud and AI. We work with clients across major industries, including Financial Services, Manufacturing, Life Sciences and Healthcare, Technology and Services, Telecom and Media, Retail and CPG, and Public Services. In this Agentic Forward Deployed Engineer role, you will work at the front line of delivery, embedded with clients to build Business Transformation Agents that automate and reimagine real business processes. You will use Python and agent development kits to bring agentic AI to life inside the client environment, with Responsible AI, evaluation and security as core expectations.

last updated 36 week of 2026