The posting
At FourKites we have the opportunity to tackle complex challenges with real-world impacts. Whether it's medical supplies from Cardinal Health or groceries for Walmart, the FourKites platform helps customers operate global supply chains that are efficient, agile and sustainable.
Join a team of curious problem solvers that celebrates differences, leads with empathy and values inclusivity.
As a Principal AI Architect, you will own the architecture underneath every FourKites AI agent: the harness they run in, the context they see, the models they call, and the evals that tell us whether they work. Our digital workers (Tracy for track and trace, Sam for supplier operations, Alan for appointment management, Cassie for customer service, Polly for document management, and more on the way) do real supply chain work on a shared platform, and you will set its direction. This is a hands-on individual contributor role based in Chennai (hybrid). You'll write code most weeks, lead design reviews across agent teams, and make the calls on model choice, context strategy and evaluation that every team builds on.
What you’ll be doing:
- Define the reference architecture for FourKites agents: the agent loop, tool execution, state and checkpointing, retries and recovery, guardrails, permissions, and human-in-the-loop handoffs
- Design for long-running, multi-step work that spans many context windows and recovers cleanly when a tool, carrier API or model call fails
- Decide where each problem is best solved (frontier LLM, open-weight model, fine-tuned encoder, or plain code) and own model routing, cost-per-task and latency budgets across the fleet
- Integrate agents with FourKites' event-driven platform (Kafka, microservices, Postgres) and with customer systems through APIs and MCP servers
- Set the standard for what goes into an agent's context window (system prompts, tool definitions, retrieved documents, memory, prior turns) within an explicit token budget
- Build shared components for retrieval, compaction and summarization, sub-agent isolation, prompt caching and persistent memory so teams stop reinventing them
- Diagnose context failures (lost instructions, tool confusion, quality degradation as the window fills) and turn fixes into reusable harness patterns
- Build the offline eval framework: golden datasets from production traces, code-based checks, LLM-as-judge graders calibrated against human labels, and CI regression suites that gate every prompt, model or tool change
- Build online evaluation: scoring sampled production traffic, trace- and task-level quality metrics, drift detection, shadow and A/B rollouts, user feedback signals, and quality alerts
- Connect eval metrics to the business outcomes customers pay for, such as tracking accuracy, exceptions resolved without a human, and appointment fill rate
- Review designs and PRs for agent teams, write the architecture docs and playbooks they follow, and mentor staff and senior engineers
- Track the model and tooling landscape, run the experiments that matter, and give leadership clear build, buy or wait recommendations
- Partner with Product, Solutions and Customer Success to turn field failures into platform fixes
About the team:
Our product and engineering teams are dedicated to providing the industry's best-in-class end-to-end supply chain visibility platform. The agent platform sits underneath every FourKites digital worker, and the teams building on it ship agents that track freight, chase suppliers, book dock appointments, answer customer questions and read shipping documents in production. You'll be the senior technical authority for how FourKites builds, ships and measures agents, working closely with agent teams in Chennai and with colleagues in the US and Europe.
Who you are:
- Agents in production : you've architected and operated at least one LLM agent system with real users and real traffic (tool calling, multi-step workflows, failure handling, human escalation) and owned it after launch through incidents, cost and latency. Framework demos and POCs alone won't be a fit
- Deep ML knowledge of encoders and transformers : attention, positional encodings, encoder-only vs decoder-only vs encoder-decoder, tokenization and the KV cache. You've trained or fine-tuned encoder models (BERT-family, sentence embeddings, bi-encoders, cross-encoder re-rankers) for classification, extraction or retrieval, and understand how contrastive training, distillation and quantization change cost and quality
- Context engineering :you've managed token budgets, built retrieval and memory for agents, used compaction and sub-agents to keep long tasks coherent, and measured how quality changes as the window fills
- Harness engineering: you've built the execution layer around a model: agent loop, tool dispatch, state and checkpoints, interruption and recovery, sandboxing and permissions, guardrails and model routing. Fluent with MCP, structured outputs and streaming
- Hands-on online and offline evals : you've built eval suites yourself: datasets, graders, LLM-as-judge calibration and CI regression gates offline; production scoring, trace sampling, drift monitoring, shadow deployments and feedback loops online. You've used evals to block a release or justify a model switch
- 10+ years building software or ML systems, with 3+ years building on LLMs
- Python: strong, hands-on. Comfortable reading and reviewing Java or TypeScript services
- Production experience on AWS or GCP, containers and Kubernetes, and event-driven systems
- Excellent oral and written communication skills: you can explain a trade-off to an engineer and its business impact to an executive
Nice to have:
- Experience in supply chain, logistics or transportation
- Document AI: OCR, layout models, and extraction from bills of lading, invoices and PODs
- Voice or email agents that act on behalf of a business
- Agent security: prompt injection defence, tool permissioning, and tenant data isolation
- Hands-on experience with several model families (Claude, GPT, Gemini, open-weight models) and serving stacks
- Published work, talks or open-source contributions on agents, retrieval or evaluation
Who we are:
FourKites, the leader in AI-driven supply chain transformation for global enterprises and pioneer of real-time visibility, turns supply chain data into automated action. FourKites Intelligent Control Tower® breaks down enterprise silos by creating a real-time digital twin of orders, shipments, inventory and assets. This comprehensive view, combined with AI-powered digital workers, enables companies to prevent disruptions, automate routine tasks and optimize performance across their supply chain. FourKites processes over 3.2 million supply chain events daily — from purchase orders to final delivery — helping 1,600-plus global brands prevent disruptions, make faster decisions and move from reactive tracking to proactive supply chain orchestration. For more information, visit www.fourkites.com.
FourKites provides competitive compensation with stock options, outstanding benefits and a collaborative culture for all employees around the globe. To help you be your best, we have 5 global recharge days, in addition to generous PTO and standard holidays. Parental leave for all parents, an annual wellness stipend and volunteer days also provide you with time and resources for self care and to care for others. Throughout the year, FourKites sets aside time during the workday to learn and celebrate diversity. We're always listening for new ways to support everyone in and out of the office.
Benefits:
- Medical benefits start on first day of employment
- 36 PTO days (Sick, Casual and Earned), 5 recharge days, 2 volunteer days
- Home Office set ups and Technology reimbursement
- Lifestyle & Family benefits
- Mental Wellness support and guidance
- Ongoing learning & development opportunities (Professional development program, Toast Master club, etc.)
FourKites is an equal opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all employees.
