Workato

Workato

Workato is the Enterprise Automation Platform that enables seamless integration and automation of workflows for both business and IT teams, utilizing AI-powered technology for efficient outcomes.

IT Services
251-1K
Founded 2013
$415M raised

Description

  • Build a unified retrieval layer across enterprise systems and expose an agent-friendly interface.
  • Design hybrid retrieval pipelines combining lexical, dense vector, and structured retrieval with re-ranking.
  • Engineer ingestion and freshness pipelines to sync millions of records with low latency and predictable cost.
  • Own permission-aware retrieval so results exactly mirror source-system access controls.
  • Build query understanding for agents, including intent parsing, entity linking, and LLM-assisted query rewriting.
  • Design chunking and embedding strategies for different content types such as documents, tickets, transcripts, and structured records.
  • Build evaluation and experimentation harnesses for retrieval quality and end-to-end agent answer quality.
  • Ship production-grade systems with strong observability, latency, freshness, recall, and cost SLOs.
  • Mentor teammates and help improve retrieval architecture, evaluation rigor, and engineering craft.

Requirements

  • 3-5 years of experience building production search, retrieval, knowledge-base, or recommendation systems.
  • Strong proficiency in at least one modern backend language such as Python, Go, or Java.
  • Hands-on experience with search engines such as OpenSearch, Elasticsearch, Solr, or Vespa, including index design and analyzers.
  • Solid grounding in IR fundamentals including TF-IDF, BM25, learning-to-rank, query parsing, and relevance evaluation.
  • Working experience with vector search and embeddings using tools such as FAISS, pgvector, Pinecone, Weaviate, Qdrant, Milvus, or native Elasticsearch/OpenSearch kNN.
  • Experience designing or contributing to RAG pipelines and semantic search systems in production.
  • Familiarity with modern NLP/LLM tooling such as transformer embeddings, cross-encoder re-rankers, prompt engineering, LangChain, LlamaIndex, or Haystack.
  • Comfort building integrations with SaaS APIs, including REST, GraphQL, webhooks, OAuth, rate limits, pagination, and incremental sync.
  • Strong intuition for ACL and permission models in enterprise systems and how to preserve them in retrieval layers.
  • Strong SQL skills, comfort with NoSQL/document stores, and experience with large-scale distributed systems.
  • Familiarity with cloud platforms such as AWS, GCP, or Azure, plus containerization and CI/CD.
  • Clear communication skills for explaining technical trade-offs to engineers, PMs, and executives.
  • Collaborative mindset with experience partnering across ML, product, security, and platform teams.
  • Quality-obsessed, detail-oriented, and comfortable driving ambiguous problems from zero to shipped.
  • Nice to have: experience with knowledge graphs, entity resolution, or cross-source identity linking.
  • Nice to have: experience tuning or fine-tuning embedding models such as sentence-transformers, BGE, or E5.
  • Nice to have: exposure to agentic AI patterns such as tool use, function calling, MCP, or multi-step retrieval planning.
  • Nice to have: experience with streaming or real-time ingestion tools such as Kafka, Flink, or Spark, and cost optimization at scale.
  • Nice to have: background in enterprise search, e-discovery, observability, or DLP.
  • Nice to have: open-source contributions, published research, or writing on retrieval, IR, or applied ML.

Benefits

  • Flexible, trust-oriented culture with strong ownership.
  • Balanced focus on productivity and self-care.
  • Vibrant and dynamic work environment.
  • Benefits that support employees inside and outside of work.
  • Recognized as the #1 best company for remote workers.

Interested in this position?

Apply directly on the company website

Apply Now

Similar Roles

Artificial Intelligence Engineer

MKS2 Technologies 51-250 Internet Software & Services

MKS2 Technologies is seeking a remote Artificial Intelligence Engineer to technically lead the design, deployment, and optimization of AI and machine learning systems supporting a federal government program.

Cybersecurity Feature Engineering Generative AI Machine Learning NLP
16 hours, 38 minutes ago

Senior Full-Stack AI Product Engineer

CGS Immersive 5001-10000 Enterprise learning

CGS is seeking a Senior Full-Stack AI Product Engineer to turn product requirements and UX concepts into polished, LLM-powered web products and evolve successful prototypes into maintainable production systems.

LLM Next.js React UX Design
17 hours, 53 minutes ago

Python/GenAI Solutions Architect

Provectus 251-1K Professional Services

Provectus is seeking a Senior Software Engineer or Solutions Architect to embed with enterprise client teams and deliver production-ready Python, cloud, and generative AI systems from discovery through deployment.

AWS CI/CD Django Docker FastAPI Flask GCP Generative AI GitHub Actions GitLab CI Go Kubernetes Machine Learning Microservices Node.js Pytest Python React REST API Rust SQL Vue.js
1 day, 17 hours ago

[Job - 31015] Master Software Developer ( AI Generative)

CI&T 5K-10K Internet Software & Services

CI&T is seeking a Master Software Developer to design, build, and scale secure, production-grade Generative AI and Agentic AI solutions for enterprise clients in a global delivery environment.

AWS Azure CI/CD Databricks Docker Generative AI Kubernetes MLOps Python Secrets Management Vertex AI
1 day, 17 hours ago

You're on a roll! Sign up now to keep applying.

Sign Up

Already have an account? Log in

Used by 14,729+ remote workers