19 Nov
|
Randstad Enterprise
|
Hyderabad
19 Nov
Randstad Enterprise
Hyderabad
What you'll do
● Own the technical design of LLM-based and agentic systems that serve Sales, Service and Supply Chain workflows, including assistants, retrieval over enterprise knowledge, tool-using agents that act against internal APIs, and document and data extraction pipelines.
● Deliver those systems into the channels people actually use: web and in-app chat, email and SMS. Own the conversational contract across them, including threading, context carry-over, handoff to a human,
and tone appropriate to the channel.
● Take ideas from prototype to production: define the architecture, break it into workstreams, and stay accountable for what ships.
● Build the parts that make AI safe to run in an enterprise: input and output guardrails, identity-aware access to tools and data, prompt versioning, and clear separation between internal and supplier-facing surfaces.
● Design and maintain the tool layer, including MCP servers and internal tool interfaces, so agents reach business systems through contracts that are versioned, permissioned and testable.
● Establish how we measure quality, including evaluation datasets, regression suites, tracing and production telemetry, so model and prompt changes are judged on evidence, not opinion.
● Own the unit economics. Track cost per conversation and per resolution, and bring it down through model routing, context trimming, caching, batching and right-sized retrieval.
● Integrate with the systems of record: ERP, supplier portals, service and CRM platforms, logistics and planning systems. Most of the difficulty in this role is integration and data, not model selection.
● Review designs and code across the team, mentor engineers,
and raise the technical bar through what you demonstrate rather than what you mandate.
Lucid Motors | 1
● Work with product and business stakeholders to decide what is worth building, and be willing to say when AI is the wrong tool for a problem.
● Partner with security, platform and infrastructure teams on deployment, cost and compliance.
What you'll bring
● 9+ years building and operating production software, with 2+ years leading the technical direction of a team or a significant system.
● Strong Python. Comfortable owning services end to end, including API design, testing, deployment and on-call reality.
● Real production experience with LLM applications: retrieval-augmented generation, agent and tool-calling patterns, structured output, streaming, prompt design and iteration.
● Strong hands-on experience with LLM engineering tooling such as Langfuse or LangSmith, used for tracing, prompt versioning, evaluation runs and production monitoring, not only local experiments.
● Good working experience with MCP: building and consuming MCP servers, designing tool schemas, and handling authentication and permissions at the tool boundary.
● Practical command of LLM cost optimization: model routing and tiering, context and prompt compression, prompt caching, batching,
token budgeting, and knowing which lever to pull when spend moves the wrong way.
● Experience delivering AI over customer and employee communication channels such as chat, email and
SMS, and the integrations behind them.
● Working knowledge of the model ecosystem and the trade-offs between hosted models, managed services and fine-tuning, enough to make a defensible choice and move on.
● Solid cloud engineering on AWS (or equivalent): serverless and container workloads, event-driven design,
IAM, networking basics, cost awareness.
● Experience with the data stores behind AI systems, relational, document and vector, and with designing retrieval that stays accurate as content grows.
● A concrete point of view on evaluating AI systems, and the discipline to build the harness before scaling the feature.
● Transparent written communication. You can explain a design to an engineer and a trade-off to a business lead in the same document.
Nice to have
● Experience in automotive, manufacturing, logistics or another operations-heavy domain.
● Exposure to SAP, supply chain execution systems, EDI, or field service and CRM platforms.
● Hands-on work with messaging and contact center platforms such as Twilio, Amazon SES or Pinpoint,
Salesforce Service Cloud, or similar.
● Background in security-sensitive AI work: prompt injection defense, data isolation between tenants or suppliers, red-teaming.
● Multi-agent orchestration, or experience running an evaluation program at scale.
● Contributions to open source, internal platforms, or published technical writing.
📌 Lead AI Engineer (Hyderabad)
🏢 Randstad Enterprise
📍 Hyderabad