Principal AI Engineer

TechGrove by Banyan Software; Bengaluru; On-site; INR 3,500,000 - 5,200,000; Full time

Job summary

TechGrove by Banyan Software in Chennai, India, seeks its first AI engineer to design the system of action on top of ProgressPlus. You will own the agent architecture, define runtime loops, and enable agents to operate with bounded authority in a compliant, auditable way.

You will lead the runtime, tool layer, and evaluation framework, integrating AI safely into manufacturing workflows and ensuring traceability for AS9100 audits.

Qualifications

• Shipped production AI or agentic systems.
• 5+ years in backend/systems engineering.
• Experience with event-driven architectures.
• Strong security and observability focus in AI.

Responsibilities

• Define architecture and standards for AI features.
• Build agent runtime and tool layers.
• Ensure auditability and AI safety in production.
• Collaborate across time zones and document standards.

Skills

Backend engineering

Event-driven

LLM integration

AI security

Team communication

Tools

C#

.NET

Azure

TypeScript

Next.js

Job description

TechGrove is the Centre of Excellence for Banyan Software, based in Chennai, India. It plays a key role in supporting Banyan’s global businesses through technology, security, and software development. TechGrove brings together India’s deep pool of technical talent with Banyan’s long-term approach to growth, creating a trusted, developer-focused environment where people can do their best work.

About Berkeley Myles

We build software for UK manufacturers who can't afford to get things wrong: aerospace, medicaldevices, oil and gas, motorsport. Our product, ProgressPlus, runs the whole job from first enquirythrough to final invoice. Hundreds of manufacturers run on it every day, and when one of them has toprove what went into a part, it's where the answer comes from. We're now building a new product withAI on every stage of that flow. We're part of Banyan Software, the best permanent home for software businesses that servespecialised industries, their employees, and their customers. Banyan is a Great Place to Work Certifiedcompany, a five-time Inc. 5000 honoree, and a top-10 company on the Deloitte Technology Fast 500. Founded in 2016 and headquartered in Atlanta, Banyan operates more than 100 portfolio companiesacross North America, the UK, the EU, and APAC.

About the Role

A manufacturer runs one flow: enquiry, quote, order, jobs, scheduling, tracking, quality, shipping,invoice. ProgressPlus is the system of record for that flow. We're building the system of action on top of it: AI that works on every stage, capturing enquiries, validating orders, optimising schedules,anticipating problems, and reconciling invoices, always with a human in control and every step auditable. You'll be the company's first AI engineer. There's not much AI in production today: no agents, noruntime, no AI layer. You'll build the system of action from a blank page. It has two parts: the events thatannounce what just happened in the business, and the agents that act on them. Agents that plan multi-step work, run in the background, act under their own identity with bounded authority, and leave a trail aregulated manufacturer can show an auditor.The ground is prepared. Five .NET services with architecture boundaries enforced in CI, and a growingcatalog of transaction-safe business operations ready to become AI tools. This is a founding role: youset the architecture, the standards and the evaluation discipline that every AI feature in this product getsbuilt on.

Key Responsibilities

• Build the agentic layer: one coherent layer that every AI capability in the product runs on. Once it exists,adding AI to any stage of the manufacturing flow is a few weeks of feature work.
• The runtime and the toolsArchitect the agent runtime: a server-side loop with durable runs, retries, scheduled and event-driventriggers, and human-in-the-loop steps
• Build the tool layer that turns our catalog of transaction-safe business operations into typed, tenant-scoped, permissioned AI tools, for our own agents and for the outside world through MCP
• Evaluation and auditMake evals part of how we ship: fixture-based tests of every AI behaviour, wired into CI from day oneClose the correction loop: every override, rejection and edit captured as structured signal, so evalsand retrieval improve from real useBuild agent auditing into the platform's tamper-evident action log as it lands: every agent steplogged, attributable and replayable. Our customers pass AS9100 audits, and explainable AI is a feature we sellGrounding and operationsDrive the event catalog: which business facts the product announces, from the office to the shopfloor (SalesOrderCreated, GoodsReceived, JobRunningLate). Every agent run starts from oneGrow the semantic grounding: a machine-readable model of the business and how it fits together, soagents retrieve facts instead of inventing them
• Own the agent authority model: what an agent may do, its budget, how much autonomy eachworkflow gets. Instrument the runtime so every step is metered and traced
• Run what you ship: your agents in production are yours, including the incident when one misbehaves

What Success Looks Like

• First three months: one real workflow runs end to end on the agent runtime in production, with itsevals in CI and every step in the audit log.
• First six months: more agents are live on the same layer, and at least one of them was built by oneof the full stack engineers.
• First twelve months: adding AI to a stage of the flow is a few weeks of feature work for anyengineer here, and you can show an auditor how any of it reached the answer it did.

How We Work

• Linear as the single board: work traced from issue to acceptance criteria to PR, reporting as a by-product of the work
• A small team: full stack engineers with a lead, plus AI and platform specialists, on a .NET and Next.jsplatform on AzurePrototype-led: we design the flow before we build it, against a shared design system
• AI in daily use across the team: coding agents in the repo with the context they need, and AI tooling for research, prototyping and analysis
• A customer base we can pick up the phone to, and an implementation team on their sites every week

Tech Stack You'll Use

• Backend: C#, .NET 10, Rebus messaging, SQL Server (database per company)
• Frontend: Next.js, React, TypeScript
• Cloud: Azure (Container Apps, Azure SQL, Service Bus, Front Door), Bicep, GitHub Actions
• AI: Model-agnostic by design, with MCP as the tool protocol
• Tooling: Claude Code, Linear, GitHub

What We're Looking For

• You've taken multiple LLM-powered systems from prototype to production, at least one of themagentic (multi-step, tool-using, running unattended), and you can walk us through what broke and
• what you'd redoProduct instincts and a builder's disposition: you can sit with a planner or a quoting manager,translate their workflow into an agent architecture without being handed a spec, then write the code,
• ship it, and talk to the people who use itStrong backend and systems engineering experience (5+ years). You've built event-driven systems,
• you can explain why the transactional outbox exists, and you think in contracts, idempotency andfailure modes
• You treat evals and observability as part of the definition of done, and you've wired LLM evaluationand observability tooling
• You treat AI security as an engineering problem: injection containment, retrieved content handledstrictly as data, and hostile inputs in the eval suite
• Clear opinions on build versus buy: you know which parts of an agent stack to take from providersand which parts you have to own
• Comfortable being first: setting standards, writing them down, and reviewing others' work againstthem
• Strong written communication: you'll work with a team split across time zones

Preferred Experience

• You've shipped something in manufacturing, ERP, supply chain or industrial operations, or you'regenuinely curious about how factories run
• Document extraction pipelines: structured extraction from PDFs and email, OCR cascades,confidence-scored human review