Description

As Principal AI Engineer, you will be the senior-most technical voice in the room on agentic AI systems, LLM applications, and AI-native product design. You will partner with the Head of Engineering, Core AI, to define architecture, set engineering standards, and personally lead the build of the most complex and highest-leverage components of the BGO AI Platform the agent runtime, the integration and orchestration layer, the Human-in-the-Loop (HITL) framework, and bespoke forward-deployed AI solutions for our enterprise clients.

You will spend the majority of your time writing code, designing systems, prototyping with frontier models, and pairing with other engineers. You will also mentor senior engineers, run architecture reviews, and act as a force multiplier across the team.

You are expected to go deep on the hardest problems reliable multi-step agent execution, evaluation, and guardrails, long-horizon memory, HITL checkpoints, and productionizing agents that operate across messy real-world client environments.

The candidate will have responsibilities across the following functions

Architecture and Platform Build :

- Own the technical architecture of the BGO AI Platform core identity, memory, knowledge graph, agent orchestration, guardrails, and audit, and lead the build of its most critical subsystems.

- Design and implement reliable, production-grade agentic workflows that execute long-running multi-step tasks with Human-in-the-Loop checkpoints, escalation paths, and graceful

failure modes.

- Define how BGO integrates frontier models, private hosted models, and BGO's domain-specific small language models (SLMs), choosing the right model for the right job and managing vendor risk across providers.

- Establish engineering standards for evaluation, observability, safety, and cost efficiency that the rest of the team builds against.

Hands-On Technical Execution :

- Personally design and ship the hardest components, agent runtimes, tool-use frameworks, RAG pipelines, fine-tuning and post-training workflows, and real-time inference infrastructure.

- Prototype rapidly against frontier models to validate new product ideas end-to-end in days, not months.

- Lead code and architecture reviews; set the bar for code quality, testing, and production readiness across the team.

- Troubleshoot and debug the hardest production issues, hallucinations, latency regressions, tool-use failures, drift, and cost blowups.

AI-Native Product and Client-Facing Work :

- Co-design and build BGO's AI-native products (e. g., Neqqo, Personal Leadership Agent, Conversational BI, Real-time Ops AI) alongside product and domain experts.

- Embed with strategic clients as a forward-deployed technical leader when needed, take the platform into client environments, customize for their data and workflows, and bring learnings back into the core.

- Design reusable, configurable building blocks so that client deployments move in days to weeks, not months.

Technical Leadership and Mentorship :

- Act as a technical force multiplier across Core AI Engineering, Internal AI & Platform Ops, and

Client Solutions / Forward-Deployed teams.

- Mentor senior and mid-level engineers; raise the technical bar through design reviews, pairing, and written RFCs.

- Represent BGO's engineering at industry events, in client conversations, and in technical hiring loops.

Responsible AI and Operational Excellence :

- Build guardrails, evaluation harnesses, and audit trails into every system from day one, not as an afterthought.

- Ensure systems meet BGO's compliance posture (ISO 27001 HIPAA, per-client isolation, role-based AI access) without slowing delivery.

- Define and track key metrics for agent reliability, model accuracy, latency, cost, and end-user impact.

Requirements :

- Bachelor's or Master's degree in Computer Science, Engineering, Mathematics, or a related technical field.

- 10+ years of professional software engineering experience with at least 4 years building and

shipping AI/ML systems in production.

- Demonstrated experience as the technical lead or principal architect on production agentic AI systems, LLM-powered agents, multi-agent workflows, tool-use frameworks, RAG, or autonomous task execution.

- Deep, hands-on expertise with the modern AI stack frontier LLMs, agent orchestration frameworks (LangChain, LangGraph, Claude Agent SDK, or equivalents), vector databases, retrieval, fine-tuning, and evaluation.

- Strong programming skills in Python and at least one additional language (TypeScript, Go, or Java), and proven ability to deliver end-to-end systems from data pipeline to production.

- Hands-on experience deploying AI systems on cloud infrastructure (AWS, GCP, or Azure) with strong DevOps, security, and observability fundamentals.

- Track record of shipping complex systems end-to-end, from ambiguous problem statement through production operation.

- Experience from top-tier technology companies (Anthropic, OpenAI, Google, Meta, Microsoft, Amazon, Flipkart) or leading AI-native startups.

- Advanced degree (MS/PhD) in Machine Learning, Computer Science, or related field.

- Prior experience in a forward-deployed, solutions engineering, or client-facing technical role where you embedded with enterprise customers and shipped bespoke AI applications.

- Experience building Human-in-the-Loop (HITL) systems review queues, escalation workflows, active learning loops, and feedback pipelines for high-stakes production use.

- Experience building and operating small language models (SLMs) or domain-fine-tuned models for compliance, classification, or operational use cases.

- Experience in enterprise BPO, contact center, customer operations, collections, insurance, or similar operationally dense domains.

- Track record of shipping AI products that drove measurable business impact, revenue, efficiency, or quality.

- Open-source contributions, publications, or public technical writing on agentic AI, LLM systems, or applied ML.

- Technical Depth The deepest technical voice in the room on agentic AI; makes architectural decisions that hold up under pressure and scale.

- Bias for Shipping Moves fast, prototypes aggressively, and gets real systems into production in weeks rather than quarters.

- High Agency Operates with founder-level autonomy in ambiguous, fast-moving environments; identifies problems and drives them to resolution without being asked.

- Force Multiplier Lifts the bar for everyone around them through mentorship, code reviews, design reviews, and written technical direction.

- Pragmatic Judgment Knows when to use agents and when not to; chooses the simplest design that meets reliability, safety, and cost requirements.

- Communication Articulates technical tradeoffs clearly to engineers, executives, and clients; writes excellent RFCs and design docs.

- Customer Obsession Deeply curious about BGO's domain collections, customer ops, sales, insurance, and comfortable sitting with clients to understand the real work.