AI Engineer

Role Summary

· Work in a scaled Agile working environment

· Be part of a global and diverse team;

· Contribute to all stages of software development lifecycle;

· Participate in peer-reviews of solution designs and related code;

· Maintain high standards of software quality within the team by following good practices and habits

· Use frameworks like Google Agent Development Kit (Google ADK) and LangGraph to build robust, controllable, and observable agentic architectures.

· Assist in the design of LLM-powered agents and multi-agent workflows (planning, tool use, orchestration, memory, and human-in-the-loop)

· Lead the implementation, deployment and test of multi-agent systems

· Mentor junior engineers on best practices for LLM engineering and agentic system development.

· Drive technical discussions and decisions related to AI architecture and framework adoption.

· Proactively identify and address technical debt and areas for improvement in AI systems.

· Represent the team in cross-functional technical discussions and stakeholder meetings.

Key Responsibilities

· Design and build complex agentic systems with multiple interacting agents.

· Implement robust orchestration logic (state machines / graphs, retries, fallbacks, escalation to humans).

· Implement RAG pipelines, tool calling, and sophisticated system prompts for optimal reliability, latency, and cost control.

· Apply core ML concepts to evaluate and improve agent performance, including dataset curation and bias/safety checks.

· Lead the development of agents using Google ADK and/or LangGraph, leveraging advanced features for orchestration, memory, evaluation, and observability.

· Integrate with supporting libraries and infrastructure (e.g., LangChain/LlamaIndex, vector databases, message queues, monitoring tools) with minimal supervision.

· Define success metrics, build evaluation suites for agents (automatic + human evaluation), and drive continuous improvement.

· Curate and maintain comprehensive prompt/test datasets; run regression tests for new model versions and prompt changes.

· Deploy and operate AI services in production, establishing CI/CD pipelines, observability, logging, and tracing.

· Debug complex failures end-to-end, identifying and document root causes across models, prompts, APIs, tools, and data.

· Work closely with product managers and stakeholders to shape requirements, translate them into agent capabilities, and manage expectations.

· Document comprehensive designs, decisions, and runbooks for complex systems.

Must-Have Qualifications

Education & experience

· 3+ years of experience as Software Engineer / ML Engineer / AI Engineer, with at least 1-2 years working directly with LLMs in real applications (not just experiments or coursework).

· Bachelor's or Master's degree in Computer Science, Engineering, Mathematics, or a related field (or equivalent practical experience).

Core technical skills:

Programming & software engineering:

· Strong proficiency in Python (core language features, packaging, testing, async, type hints).

· Very strong software engineering practices: version control (Git), unit/integration testing, code reviews, CI/CD.

· Experience building and consuming REST/gRPC APIs and integrating external tools/services.

Machine Learning (good understanding):

· Understanding of core ML concepts: supervised/unsupervised learning, train/validation/test splits, overfitting, regularization, and common metrics (precision, recall, F1, ROC-AUC, etc.).

· Good undeerstanding of deep learning basics (neural networks, embeddings) and at least one ML/DL framework (e.g., PyTorch, TensorFlow, JAX, scikit-learn).

LLMs & agentic AI (very strong understanding):

· Deep practical knowledge of large language models:

· Tokenization, context windows, temperature, top-p, system vs user prompts.

· Prompt engineering patterns (ReAct, chain-of-thought, tool-calling/tool-use).

· Fine-tuning / adapters / instruction-tuning, or experience with RAG as an alternative.

· Experience building LLM-powered applications end-to-end: from idea → prototype → production.

· Familiarity with safety and reliability considerations: hallucinations, guardrails, content filtering, privacy.

Agentic frameworks (required understanding, experience preferred):

· Conceptual understanding of modern agentic frameworks and patterns (stateful graphs, multi-agent coordination, human-in-the-loop, memory, and evaluation).

· Hands-on experience with at least one of:

o Google Agent Development Kit (ADK) – building multi-agent workflows, using its orchestration, tools, and evaluation features.

o LangGraph – designing graph-based, stateful agent workflows with cycles, branches, and durable execution.

· Candidates must be able to read, reason about, and extend ADK/LangGraph-based codebases.

· Direct production experience with both ADK and LangGraph is a strong plus.

Data & infra:

· Experience working with vector databases (e.g., Pinecone, Weaviate, pgvector, Chroma) for retrieval-augmented generation.

· Comfortable with SQL and basic data modeling.

· Experience deploying on at least one major cloud platform (GCP, AWS, Azure) and using managed services (e.g., serverless runtimes, container orchestration, secrets management).

Soft skills:

· Ability to translate ambiguous business requirements into concrete technical designs.

· Strong communication skills; able to explain trade-offs to both technical and non-technical stakeholders.

· Comfort working in an experimental environment with rapid iteration, but with a strong bias towards production quality and maintainability.

Nice-to-Have

Experience with:

· Vertex AI / Gemini or other hosted LLM ecosystems.

· Related frameworks and tools: LangChain, LlamaIndex, semantic search, evaluation frameworks (e.g., RAGAS, custom eval harnesses).

· Monitoring and observability stacks (OpenTelemetry, Prometheus/Grafana/NewRelic, Datadog, etc.).

Background in one or more of:

· Information retrieval / search.

· NLP (beyond LLMs): classic text processing, embeddings, semantic similarity.

· Security & compliance for AI systems (PII handling, access control, audit logging).

· Contributions to open-source AI projects, blog posts, or talks about LLMs/agentic systems.

What We Offer

· Opportunity to work on real-world agentic AI systems with modern frameworks (Google ADK, LangGraph, Vertex AI, etc.).

· Tight collaboration with a small, senior engineering and product team.

· Budget for learning (conferences, courses, books) specifically around agentic AI, LLMs, and MLOps.

· Competitive salary, equity, and flexible/remote work options.