Full-time · Remote (India)

Neurosymbolic Marketing Intelligence Engineer

Build AI systems that fuse neural patterns with symbolic reasoning to decode marketing intelligence and drive intelligent campaigns.

About the role

You will design and deploy neurosymbolic AI systems that combine the pattern-recognition power of neural networks with the explainability and rule-based precision of symbolic reasoning — turning raw marketing data into actionable, interpretable intelligence. Your work will directly influence campaign strategy, customer segmentation, and real-time decisioning across enterprise clients.

What you will do

  • Architect and implement neurosymbolic models that integrate neural representations with symbolic knowledge graphs for marketing attribution and audience understanding.
  • Develop NLP pipelines and LLM integration layers to extract structured insights from unstructured marketing content — emails, surveys, social signals, and campaign copy.
  • Build and maintain marketing analytics dashboards and real-time intelligence APIs serving segmentation, propensity scoring, and next-best-action recommendations.
  • Collaborate with product and growth teams to embed AI-driven marketing intelligence into client platforms, ensuring explainability and compliance with data-privacy regulations.
  • Design evaluation frameworks using controlled experiments, counterfactual analysis, and causal inference to measure model impact on marketing KPIs.
  • Mentor junior engineers and contribute to internal research on hybrid AI approaches for vertical-specific marketing use cases.

What you should know

  • Fundamentals of neurosymbolic AI: understand how deep learning and symbolic logic can be unified — rules, ontologies, and neural embeddings working in concert.
  • Core statistical and causal inference techniques: causal graphs, do-calculus, and counterfactual reasoning as applied to marketing mix modelling and uplift estimation.
  • Marketing science foundations: customer journey mapping, attribution models (first-touch, last-touch, Markov, Shapley), and lifetime value (LTV) estimation.

What you should be able to do

  • Python — proficiency with PyTorch/JAX, LangChain/LlamaIndex, and graph libraries like NetworkX or PyG.
  • Knowledge-graph tooling — Neo4j, RDF/SPARQL, OWL/DL reasoning, and vector-database integration (e.g., Milvus, Weaviate).
  • MLOps and production deployment — MLflow, Kubeflow, Docker/Kubernetes, CI/CD for ML pipelines on AWS SageMaker or equivalent.
  • Marketing analytics stacks — SQL, dbt, Looker/Metabase, and experience with CDPs (Customer Data Platforms) like Segment or mParticle.
  • LLM orchestration and RAG — prompt engineering, function calling, retrieval-augmented generation, and guardrail implementation.

How you work

  • A compulsive habit of reverse-engineering why a model's recommendation diverged from the ground-truth marketing outcome — pursuing interpretability over accuracy alone.
  • Regularly exploring the intersection of cognitive science and AI — drawing analogies between human heuristic reasoning and symbolic rule systems.
  • An instinct for turning vague business questions (e.g., 'Why are our email open rates dropping?') into testable AI hypotheses with measurable feedback loops.

Skills we check

  • Neurosymbolic AI & Hybrid Reasoning
  • Machine Learning & Deep Learning
  • Marketing Data Analytics & Attribution
  • Natural Language Processing (NLP)
  • Knowledge Graphs & Ontologies
  • Python & MLOps
  • Cloud Platforms (AWS/Azure/GCP)
  • A/B Testing & Statistical Modelling

What you get

  • Competitive annual CTC of ₹12L–₹20L with performance-based bonuses and ESOP eligibility.
  • Fully remote-first setup with a home-office stipend and annual tech-budget allowance.
  • Access to dedicated GPU cloud credits (A100/H100 hours) for personal research and side projects.
  • Structured mentorship from senior AI researchers and bi-weekly tech-salon sessions on emerging neurosymbolic literature.
  • Sabbatical-style learning weeks twice a year — paid time off dedicated to conference attendance, certifications, or independent R&D.

How we select for this role

Every stage happens in the portal, and you can see where you stand at any time.

  1. Apply on the portal

    Sign in, upload your CV (PDF or Word), confirm your details and sign the candidate undertaking. About ten minutes.

  2. CV review

    Your CV is read against this role's requirements, usually within a few minutes. If it is not a fit, you see that in the portal with the reason.

  3. Written questions and integrity check

    Around ten technical questions written for your CV and this role, answered in the portal with paste turned off. An automated check confirms the answers were typed by you, and you see the result before you submit.

  4. Shortlisted: choose your date

    If no cheating is detected you are shortlisted straight away, and we email you a link to choose the day your practical project starts.

  5. 5-day practical project

    On that day our team contacts you with the brief: real work for 5 working days, reviewed by an engineer. For this role: Over 5 working days, you will be given a synthetic B2B marketing dataset (lead-scoring features, campaign touchpoints, and conversion outcomes). You must: (Day 1–2) build a knowledge graph representing the customer journey and a neurosymbolic model that combines embedding-based similarity with rule-based segment definitions; (Day 3–4) produce an explainable propensity-to-convert prediction engine with SHAP/LIME attribution and a RAG layer that surfaces reasoning traces; (Day 5) present a live demo and write-up covering architecture decisions, evaluation metrics (AUC, calibration, interpretability score), and a plan for production deployment. Evaluation focuses on correctness, clarity of reasoning, and production-readiness of the approach.

  6. Offer

    If your work solves the problem well, your offer letter is issued in the portal and by email.