Why This Job is Featured on The SaaS Jobs
This Senior Lead Machine Learning Engineer role stands out in SaaS because it sits at the intersection of agentic AI and semantic search—capabilities increasingly embedded in modern SaaS products as “native” decisioning and automation layers. The remit implies production-grade AI that must perform under real-time constraints and be accountable to measurable outcomes, a common pressure point for SaaS platforms serving revenue-critical workflows.
From a SaaS career perspective, the work maps to durable platform-building skills: designing retrieval and reasoning systems, establishing evaluation and feedback loops, and instrumenting quality metrics that can be tracked over time. Experience with RAG pipelines, hybrid search, and vector infrastructure translates across many SaaS categories adopting LLM-enabled features, while the emphasis on benchmarking and continuous improvement aligns with how SaaS teams operationalise ML beyond prototypes.
The role is best suited to an experienced engineer who prefers hands-on technical leadership and making architectural decisions that other teams build upon. It fits someone comfortable balancing research-informed approaches with reliability, latency, and observability expectations typical of customer-facing SaaS. Candidates who enjoy cross-functional partnership—especially turning ambiguous AI capabilities into repeatable systems—are likely to find the scope well matched.
The section above is editorial commentary from The SaaS Jobs, provided to help SaaS professionals understand the role in a broader industry context.
Job Description
We are seeking a highly skilled senior technical lead to join our Agentic AI & Semantic Search team. This is a hands-on technical leadership role responsible for designing scalable AI systems that integrate agentic reasoning with semantic search to deliver real-time, context-rich, and commerce-aware decisions.
You will define the technical vision, lead architectural strategy, and build retrieval, reasoning, and evaluation platforms that directly impact how the world’s top brands manage billions of dollars in eCommerce revenue.
Key Responsibilities
- Architecture & Leadership: Define and drive the architecture for agentic AI systems that combine LLM reasoning, semantic search, and contextual grounding.
- AI Agent Development: Design frameworks that allow agents to autonomously analyze data, retrieve context, and execute workflows across e-commerce platforms.
- Semantic Search Excellence: Build scalable retrieval systems leveraging vector databases, embeddings pipelines, hybrid search (dense + sparse), and re-ranking models.
- Agent-Oriented Design: Enable agents to access structured and unstructured commerce data (retailer catalogs, customer demand, supply chain signals) with contextual reasoning and memory.
AI Flywheel & Continuous Improvement:
- Design and operationalize evaluation datasets and benchmarking frameworks for agents and semantic search.
- Integrate annotation and labeling workflows to generate high-quality training and evaluation datasets.
- Build feedback loops where customer signals and agent outcomes drive system improvements.
- Metrics & Instrumentation: Define robust metrics for search relevance, grounding accuracy, reasoning quality, and business impact.
- Scalable Infrastructure: Architect distributed, low-latency, production-grade AI systems that serve mission-critical to CommerceIQ use cases.
- Cross-team Collaboration: Partner with Agentic AI engineers, and product managers to turn AI innovations into scalable solutions.
- Mentorship & Influence: Provide technical guidance, mentor engineers, and champion best practices in system design and AI engineering.
Qualifications
Must-Have
- 8-10+ years of software engineering experience, including 3+ years in Senior IC roles.
- In-depth knowledge of LLMs, agent frameworks, orchestration (LangChain, LlamaIndex, CrewAI, etc.), and retrieval-based methods.
- Experience in semantic search, retrieval systems, and distributed system design.
- Strong expertise in vector DBs (FAISS, Pinecone, Weaviate, Milvus), hybrid search, embeddings, and re-ranking models.
- Proven track record with RAG pipelines and integrating retrieval into LLM reasoning.
- Familiarity with evaluation dataset design, annotation tools (Labelbox, Scale AI, Prodigy, or in-house), and developing continuous evaluation pipelines.
- Proficient in Python and at least one systems language (Go, Java, or C++).
- Strong background in system design with the ability to lead end-to-end technical initiatives.
Nice-to-Have
- Experience with LLM fine-tuning, alignment, or reinforcement learning with human feedback (RLHF).
- Background in NLP/IR research, query understanding, or contextual search optimization.
- Experience with eCommerce / retail datasets and domain-specific semantic search challenges.
What We Value
- Commerce-First AI: Passion for applying AI to solve real-world commerce problems.
- Builder Mindset: Thrives in ambiguity and can translate vision into scalable systems.
- Pragmatic Innovation: Balances cutting-edge research with enterprise-grade reliability.
- Leadership Without Authority: Influences across teams through technical depth and clarity.
