Job Details:

Job Description:

We are seeking a highly skilled, hands-on Senior Agentic AI & Automation Engineer to design, build, and scale our next-generation autonomous validation workflows. In this role, you will move beyond rigid, rule-based automation scripts to architect dynamic, context-aware AI ecosystems. You will be responsible for building multi-agent frameworks where autonomous software entities plan, reason, use enterprise tools, and execute complex FPGA Configuration & Security Firmware validation workflows based on Altera FPGA customer use-cases.

As a senior engineer, you will own the technical implementation from ideation to production, write clean and resilient code, and mentor junior team members on AI engineering best practices.

The successful candidate will be part of the Altera Software and IP Solutions (SIPS) Team.

Why this Role Matters?

The tech industry is moving past basic chatbots and rigid, rule-based automation. The next frontier is Agentic AI—systems that don't just answer questions, but independently reason, plan, and execute complex validation workflows.

As a Senior Engineer here, you won't just be maintaining legacy pipelines or writing boilerplate validation automaton scripts; you will be the foundational architect of this shift. You will have the rare opportunity to bridge the gap between bleeding-edge AI research and production-grade engineering, shaping how our entire enterprise operates.

If you want to move past the AI hype and actually build the autonomous systems defining the next decade of software engineering, this is where you do it.

Key Responsibilities

• Design & Develop Agentic Systems: Architect, build, and deploy production-grade multi-agent systems and cognitive workflows using frameworks like LangGraph, CrewAI, AutoGen, or custom orchestration layers
• Enterprise Tool Integration: Build secure, high-performance connectors, APIs, and middleware that allow AI agents to interact seamlessly with legacy systems, databases, vector stores, and third-party SaaS applications
• RAG & Context Optimization: Implement and optimize advanced Retrieval-Augmented Generation (RAG) pipelines, chunking strategies, and vector database schemas (e.g., Pinecone, Milvus, Qdrant) to provide agents with accurate, real-time context
• Hardening & Guardrails: Design and implement rigid validation layers, cost-tracking controls, and evaluation frameworks (e.g., Ragas, LangSmith) to prevent hallucination, control API spend, and ensure deterministic outcomes from non-deterministic LLMs
• Code Quality & CI/CD: Establish robust CI/CD pipelines, automated testing (unit, integration, and LLM-as-a-judge evaluations), and monitoring infrastructure for autonomous agents
• Technical Mentorship: Act as a subject matter expert across the organization, conducting code reviews, defining engineering standards, and mentoring mid-level developers on AI patterns.

Qualifications:

• Bachelor's/Master's or PhD degree in Electrical Engineering, Computer Engineering, Computer Science or related field
• Firmware/Embedded Software Validation Excellence: 8+ years of professional experience validating complex FPGA user flows on pre‑silicon and/or post‑silicon platforms. Deep expertise in firmware/embedded software testing, strong analytical skills, and a passion for delivering high‑quality products.  Strong understanding of embedded systems, microcontrollers, SoCs, and low-level firmware architecture and software stack layers 

• Core Software Engineering Foundation: 15+ years of professional software engineering experience, with a heavy emphasis on Python or TypeScript/Node.js. Deep understanding of async programming, concurrency, and design patterns
• Production AI Experience: 1+ years of hands-on experience building applications powered by LLMs (OpenAI, Anthropic, open-source models). Proven track record of moving an AI-driven project from a local prototype to a scaled production environment
• Data & Infrastructure: Proficient with SQL/NoSQL databases, vector databases, and containerization (Docker, Kubernetes). Experience deploying AI workloads on cloud infrastructure (AWS, GCP, or Azure)
• Problem Solver: Ability to analyse complex, unstructured business processes and translate them into modular, resilient, and autonomous software architectures

In addition to these skills, one or more of the following skills will be an added advantage

• Agentic Framework Mastery: Expert-level knowledge of orchestrating stateful, multi-agent architectures, function calling, tool usage, and prompt engineering/tuning
• Prompt Engineering & Alignment: Advanced prompt engineering skills, including Few-Shot prompting, Chain-of-Thought (CoT), and ReAct frameworks, alongside experience fine-tuning small, open-source models (e.g., Llama 3, Mistral) for specific automation sub-tasks
• Advanced RAG & Data Engineering: Experience implementing advanced Retrieval-Augmented Generation (RAG) techniques (e.g., hybrid search, parent-document retrieval, hypothetical document embeddings/HyDE, and re-ranking pipelines) using vector databases like Pinecone, Qdrant, Milvus, or pgvector.
• API Synthesis & Function Calling: Mastery of teaching LLMs to reliably use external tools via strict JSON schema function calling, handling API rate limits, backoffs, and complex authentication flows autonomously
• Agile Prototyping with a Production Mindset: A strong track record of rapidly building functional Proof of Concepts (PoCs) to test agent feasibility, while simultaneously architecting the underlying code cleanly enough to scale into enterprise-grade software.

Job Type:

Shift:

Primary Location:

Additional Locations:

Posting Statement: