Solutions Manager (IN)
HCLTech
HCLTech
Join us as an Agentic Forward Deployed Engineer, operating at the forefront of innovation. You'll be embedded with clients, transforming complex business challenges into robust production agents swiftly. The core of your work involves building Business Transformation Agents – autonomous, multi-agent systems designed to automate and revolutionize essential business processes like invoice disputes, procurement, onboarding, claims, and compliance.
You will take complete ownership of each agent, from conception and development through integration, evaluation, deployment, and ongoing support. This role also involves leading a small, dedicated team of engineers through these phases. Development is exclusively in Python, utilizing advanced agent development kits, and you will integrate Agentic AI capabilities within client environments, prioritizing Responsible AI, rigorous evaluation, and security.
Key responsibilities include rapid conceptualization by embedding with stakeholders to frame business processes as agentic solutions and developing functional prototypes within days. You will build and deploy single- and multi-agent systems in Python using ADKs, focusing on measurable ROI and driving both delivery and operational efficiency through shorter cycles, reduced manual effort, higher accuracy, and lower cost-to-serve.
Your role involves engineering the agent core using techniques such as prompt engineering, RAG, memory, tool calling, and multi-agent orchestration. You'll ensure seamless integration into client ecosystems via standards-based APIs and secure authentication. Emphasis will be placed on creating reusable agent components, skills, and templates, while implementing guardrails for predictable, safe, and repeatable agent behavior.
Furthermore, you will engage in rapid prototyping and iteration, hardening initial concepts into production-grade Python code. Eval-driven development is crucial, requiring the construction of evaluation harnesses and test suites to measure agent correctness and safety. You will own AgentOps/DevSecOps, encompassing CI/CD, versioning, observability, and Responsible AI governance from the outset. Maintaining an adaptable feedback loop by integrating production telemetry and client feedback into agent design is essential.
Continuously staying abreast of evolving agent frameworks and patterns, and bringing field learnings back to the practice is expected. You will also lead and mentor a lean team of 3 agent engineers, setting technical direction, elevating engineering standards, and growing the pod's agentic capabilities.
We are seeking individuals with strong Python engineering skills, emphasizing idiomatic, typed, tested, and packaged code built on solid software engineering principles. Essential experience includes hands-on agent building with at least one agent development kit (e.g., Google ADK, LangGraph, CrewAI, OpenAI Agents SDK, AWS Bedrock AgentCore, or Microsoft Agent Framework/Semantic Kernel). A solid command of agent engineering concepts such as prompt engineering, RAG, tool/function calling, and multi-agent orchestration is vital.
Proficiency in eval-driven development for measuring agent quality and safety, alongside expertise in standards-based integration and DevSecOps (APIs, secure authentication, CI/CD, observability, AgentOps) is required. The ability to quickly conceptualize business problems as agentic solutions and operate effectively in ambiguous, client-embedded settings is key. Strong client-facing maturity, translating effectively between technical and non-technical stakeholders, and owning outcomes are also necessary qualifications. Prior experience mentoring or leading small engineering teams is a must-have.
While Python is the preferred language, fluency across multiple ADKs and the judgment to select the appropriate one for an engagement are strongly preferred. Experience deploying agents to managed runtimes at enterprise scale with governance and cost control, as well as domain depth in areas like finance operations, supply chain, HR, claims, or compliance, are highly advantageous. A proven track record of developing reusable agent accelerators or intellectual property adopted beyond a single engagement, and experience with enterprise agent platforms including Responsible AI and governance at scale, are considered significant strengths.
HCLTech
IT Consulting