AI Architect

Oppurtuna; Chennai District; Hybrid; INR 5,000,000 - 8,000,000; Full time

Benefits offered by this job

Medical benefits from day one

36 PTO days

Home Office setup & tech reimbursement

Job summary

FourKites is seeking an Principal AI Architect to own the architecture of AI agents that power digital workers across logistics workflows. Based in Chennai with hybrid work, you will design the agent loop, memory, and tool integrations, and guide model routing, cost per task, and latency budgets.

You will lead cross-team reviews and shape platform direction. You will build shared components for retrieval, memory, and prompt caching, and mentor engineers while partnering with Product and Customer

Qualifications

• Experience architecting and operating LLМ agent systems with real traffic.
• Strong knowledge of encoders, transformers, and memory management for long-running tasks.
• Hands-on experience with model routing, tool dispatch, and evaluation pipelines.

Responsibilities

• Define reference architecture for FourKites agents and their contexts.
• Lead design reviews across agent teams and set evaluation standards.
• Build offline and online eval suites with CI gates and A/B testing.
• Collaborate with Product and Solutions to translate field failures into platform improvements.

Skills

Python

LLM agents

Cloud services

Kubernetes

Architecture design

Education

Bachelor's degree in CS/Engineering

Tools

AWS

GCP

PostgreSQL

Kafka

MCP

Job description

# AI ArchitectFourkitesChennai or RemotePosted 19 hours agoApply Now## DetailsLocationChennai or Remote## Job SummaryEngineering, India## Job DescriptionAt 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 handoffsDesign for long-running, multi-step work that spans many context windows and recovers cleanly when a tool, carrier API or model call failsDecide 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 fleetIntegrate agents with FourKites' event-driven platform (Kafka, microservices, Postgres) and with customer systems through APIs and MCP serversSet the standard for what goes into an agent's context window (system prompts, tool definitions, retrieved documents, memory, prior turns) within an explicit token budgetBuild shared components for retrieval, compaction and summarization, sub-agent isolation, prompt caching and persistent memory so teams stop reinventing themDiagnose context failures (lost instructions, tool confusion, quality degradation as the window fills) and turn fixes into reusable harness patternsBuild 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 changeBuild online evaluation: scoring sampled production traffic, trace- and task-level quality metrics, drift detection, shadow and A/B rollouts, user feedback signals, and quality alertsConnect eval metrics to the business outcomes customers pay for, such as tracking accuracy, exceptions resolved without a human, and appointment fill rateReview designs and PRs for agent teams, write the architecture docs and playbooks they follow, and mentor staff and senior engineersTrack the model and tooling landscape, run the experiments that matter, and give leadership clear build, buy or wait recommendationsPartner with Product, Solutions and Customer Success to turn field failures into platform fixesAbout 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 fitDeep 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 qualityContext 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 fillsHarness 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 streamingHands-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 switch10+ years building software or ML systems, with 3+ years building on LLMsPython: strong, hands-on. Comfortable reading and reviewing Java or TypeScript servicesProduction experience on AWS or GCP, containers and Kubernetes, and event-driven systemsExcellent oral and written communication skills: you can explain a trade-off to an engineer and its business impact to an executiveNice to have:Experience in supply chain, logistics or transportationDocument AI: OCR, layout models, and extraction from bills of lading, invoices and PODsVoice or email agents that act on behalf of a businessAgent security: prompt injection defence, tool permissioning, and tenant data isolationHands-on experience with several model families (Claude, GPT, Gemini, open-weight models) and serving stacksPublished work, talks or open-source contributions on agents, retrieval or evaluationWho 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 employment36 PTO days (Sick, Casual and Earned), 5 recharge days, 2 volunteer daysHome Office set ups and Technology reimbursementLifestyle & Family benefitsMental Wellness support and guidanceOngoing 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.